backtest
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill is subject to indirect prompt injection (Category 8) because it processes untrusted financial market data. Ingestion points: market data from 'polymarket' or other providers (SKILL.md). Boundary markers: absent; no mechanisms are described to distinguish data from instructions. Capability inventory: the engine executes strategy logic via the 'onData' callback and performs complex numerical analysis (SKILL.md). Sanitization: absent; data is processed in its raw form.
- Dynamic Execution (LOW): The framework allows users to define custom strategy behavior using asynchronous JavaScript functions (Category 10), providing a controlled surface for dynamic execution of logic during the backtesting process.
Audit Metadata